Speech enhancement and speech separation are two related tasks, whose purpose is to
extract either one or more target speech signals, respectively, from a mixture of sounds …

Speech enhancement has benefited from the success of deep learning in terms of
intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods …

Supervised deep learning has gained significant attention for speech enhancement recently.
The state-of-the-art deep learning methods perform the task by learning a ratio/binary mask …

Recent studies have shown that acoustic beamforming using a microphone array plays an
important role in the construction of high-performance automatic speech recognition (ASR) …

This work proposes a neural network to extensively exploit spatial information for
multichannel joint speech separation, denoising and dereverberation, named SpatialNet. In …

Speech separation has been studied widely for single-channel close-talk microphone
recordings over the past few years; developed solutions are mostly in frequency-domain …

Hand-crafted spatial features (eg, inter-channel phase difference, IPD) play a fundamental
role in recent deep learning based multi-channel speech separation (MCSS) methods …

In recent years time domain speech separation has excelled over frequency domain
separation in single channel scenarios and noise-free environments. In this paper we …

To date, mainstream target speech separation (TSS) approaches are formulated to estimate
the complex ratio mask (cRM) of target speech in time-frequency domain under supervised …

Existing machine learning research has achieved promising results in monaural audio-
visual separation (MAVS). However, most MAVS methods purely consider what the sound …